sample.sql_in

Go to the documentation of this file.

/* ----------------------------------------------------------------------- *//**
 *
 * @file sample.sql_in
 *
 * @brief SQL functions for random sampling
 *
 * @sa For an overview of random-sampling functions, see the module
 *     description \ref grp_sample.
 *
 *//* ----------------------------------------------------------------------- */

m4_include(`SQLCommon.m4')

/**
@addtogroup grp_sample

\warning <em> This MADlib method is still in early stage development. There may be some 
issues that will be addressed in a future version. Interface and implementation
is subject to change. </em>

@about

The random sampling module consists of useful utility functions for sampling
operations. Several of these functions can be used while implementing 
new algorithms.

Refer to the file for documentation on each of the utlity functions.

@sa File sample.sql_in documenting the SQL functions.
*/

CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_transition_int64(
    state MADLIB_SCHEMA.bytea8,
    value BIGINT,
    weight DOUBLE PRECISION
) RETURNS MADLIB_SCHEMA.bytea8
AS 'MODULE_PATHNAME'
LANGUAGE C
VOLATILE
STRICT;

CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_merge_int64(
    state_left MADLIB_SCHEMA.bytea8,
    state_right MADLIB_SCHEMA.bytea8
) RETURNS MADLIB_SCHEMA.bytea8
AS 'MODULE_PATHNAME'
LANGUAGE C
VOLATILE
STRICT;

CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_final_int64(
    state MADLIB_SCHEMA.bytea8
) RETURNS BIGINT
AS 'MODULE_PATHNAME'
LANGUAGE C
IMMUTABLE
STRICT;

/**
 * @brief Sample a single row according to weights
 *
 * @param value Value of row. Uniqueness is not enforced. If a value occurs
 *     multiple times, the probability of sampling this value is proportional to
 *     the sum of its weights.
 * @param weight Weight for row. A negative value here is treated has zero
 *     weight.
 * @return \c identifier of the selected row. The probability of sampling any
 *     particular row <tt>(value, weight)</tt> is
 *     <tt>weight/SUM(weight)</tt>.
 */
CREATE AGGREGATE MADLIB_SCHEMA.weighted_sample(
    /*+ value */ BIGINT,
    /*+ weight */ DOUBLE PRECISION) (

    SFUNC=MADLIB_SCHEMA.weighted_sample_transition_int64,
    STYPE=MADLIB_SCHEMA.bytea8,
    FINALFUNC=MADLIB_SCHEMA.weighted_sample_final_int64,
    m4_ifdef(`__GREENPLUM__',`prefunc=MADLIB_SCHEMA.weighted_sample_merge_int64,')
    INITCOND=''
);


CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_transition_vector(
    state MADLIB_SCHEMA.bytea8,
    value DOUBLE PRECISION[],
    weight DOUBLE PRECISION
) RETURNS MADLIB_SCHEMA.bytea8
AS 'MODULE_PATHNAME'
LANGUAGE C
VOLATILE
STRICT;

CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_merge_vector(
    state_left MADLIB_SCHEMA.bytea8,
    state_right MADLIB_SCHEMA.bytea8
) RETURNS MADLIB_SCHEMA.bytea8
AS 'MODULE_PATHNAME'
LANGUAGE C
VOLATILE
STRICT;

CREATE FUNCTION MADLIB_SCHEMA.weighted_sample_final_vector(
    state MADLIB_SCHEMA.bytea8
) RETURNS DOUBLE PRECISION[]
AS 'MODULE_PATHNAME'
LANGUAGE C
IMMUTABLE
STRICT;

CREATE AGGREGATE MADLIB_SCHEMA.weighted_sample(
    /*+ value */ DOUBLE PRECISION[],
    /*+ weight */ DOUBLE PRECISION) (

    SFUNC=MADLIB_SCHEMA.weighted_sample_transition_vector,
    STYPE=MADLIB_SCHEMA.bytea8,
    FINALFUNC=MADLIB_SCHEMA.weighted_sample_final_vector,
    m4_ifdef(`__GREENPLUM__',`prefunc=MADLIB_SCHEMA.weighted_sample_merge_vector,')
    INITCOND=''
);